© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25609
    Prev
    Next
    INDEX
    Explanations

    introducing a concept or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MEJOR
    -0.94
     otwar
    -0.90
     sài
    -0.86
     TÉCNICA
    -0.84
     NUEVO
    -0.83
     jonge
    -0.83
     estándar
    -0.83
    nell
    -0.82
    ereza
    -0.82
     desemple
    -0.82
    POSITIVE LOGITS
     "
    1.12
     “
    1.10
     tzw
    1.09
     sogenannten
    1.08
     sogenannte
    1.02
    reverse
    1.00
     '
    0.93
     so
    0.91
     pseudo
    0.89
     hybrid
    0.86
    Activations Density 0.284%

    No Known Activations